© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56221
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "the top of" and related expressions indicating elevated positions or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿·
    -0.07
    565
    -0.07
    259
    -0.06
    огÑĥ
    -0.06
    zb
    -0.06
    ago
    -0.06
     Pepper
    -0.06
     Gordon
    -0.05
    rels
    -0.05
     Cov
    -0.05
    POSITIVE LOGITS
    íŀ
    0.08
    .hwp
    0.08
    ROKE
    0.08
    ạn
    0.07
    cales
    0.07
    à¤ķरण
    0.07
    werk
    0.07
    sterol
    0.07
    ynet
    0.07
    chop
    0.07
    Activations Density 0.013%

    No Known Activations